From abfc0410a2385d8c3d6ee1915fc99b708e1d0dbc Mon Sep 17 00:00:00 2001 From: Muriithi Frederick Muriuki Date: Wed, 1 Sep 2021 10:49:52 +0300 Subject: Built top-level genotype file parsing function Issue: https://github.com/genenetwork/gn-gemtext-threads/blob/main/topics/gn1-migration-to-gn2/clustering.gmi * gn3/db/genotypes.py: parse genotype files * tests/unit/db/test_genotypes.py: test parsing is correct Add the overall genotype files parsing function and tests to check that the parsing works as expected. --- gn3/db/genotypes.py | 38 +++++++++++++++++++++++++++++++++++++- 1 file changed, 37 insertions(+), 1 deletion(-) (limited to 'gn3/db') diff --git a/gn3/db/genotypes.py b/gn3/db/genotypes.py index 8710d2e..b5d14a5 100644 --- a/gn3/db/genotypes.py +++ b/gn3/db/genotypes.py @@ -107,7 +107,7 @@ def parse_genotype_header(line: str, parlist = tuple()): ("prgy", prgy), ("nprgy", len(prgy))) -def parse_genotype_data_line(line: str, geno_obj: dict, parlist: list): +def parse_genotype_marker(line: str, geno_obj: dict, parlist: list): """ Parse a data line in a genotype file @@ -143,3 +143,39 @@ def parse_genotype_data_line(line: str, geno_obj: dict, parlist: list): ("cM", cM), ("Mb", float(geno_obj["mb_column"]) if geno_obj["Mbmap"] else None), ("genotype", genotype)) + +def build_genotype_chromosomes(geno_obj, markers): + """ + Build up the chromosomes from the given markers and partially built geno + object + """ + mrks = [dict(marker) for marker in markers] + chr_names = {marker["chr"] for marker in mrks} + return tuple(( + ("name", chr_name), ("mb_exists", geno_obj["Mbmap"]), ("cm_column", 2), + ("mb_column", geno_obj["mb_column"]), + ("loci", tuple(marker for marker in mrks if marker["chr"] == chr_name))) + for chr_name in sorted(chr_names)) + +def parse_genotype_file(filename: str, parlist = tuple()): + """ + Parse the provided genotype file into a usable pytho3 data structure. + """ + with open(filename, "r") as infile: + contents = infile.readlines() + + lines = tuple(line for line in contents if + ((not line.strip().startswith("#")) and + (not line.strip() == ""))) + labels = parse_genotype_labels( + line for line in lines if line.startswith("@")) + data_lines = tuple(line for line in lines if not line.startswith("@")) + header = parse_genotype_header(data_lines[0], parlist) + geno_obj = dict(labels + header) + markers = tuple( + parse_genotype_marker(line, geno_obj, parlist) + for line in data_lines[1:]) + chromosomes = tuple( + dict(chromosome) for chromosome in + build_genotype_chromosomes(geno_obj, markers)) + return {**geno_obj, "chromosomes": chromosomes} -- cgit v1.2.3